Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mtarcure/claude-vibe-squad --skill parser-differential-route-confusiongit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mtarcure/claude-vibe-squad/parser-differential-route-confusion)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/parser-differential-route-confusion"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/parser-differential-route-confusion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/parser-differential-route-confusion"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/parser-differential-route-confusion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00678 |
| Opus 5.5 | $0.00022 | $0.00271 |
| Sonnet 5.5 | $0.00011 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
parser-differential-route-confusion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parser-Differential Route Confusion
Audit API gateways, batch processors, and microservice routers for route/permission desynchronization: one component validates a request's route/permissions using one parser while a different component executes it using another, so a nested or crafted path passes auth as a "safe" route but resolves at execution to a privileged one. Chain with a downstream injection (SQLi/command) reachable only through the confused route for pre-auth RCE.
Source: corpus A §I.2 — Assetnote "wp2shell" (CVE-2026-63030 / CVE-2026-60137): WordPress
/wp-json/batch/v1 validated nested routes in one loop and executed in another; a wp_parse_url()
path discrepancy let an unauthenticated batch sub-request execute against a privileged admin route,
chained to author__not_in SQLi → admin creation → webshell.
Impact class: RCE / privilege escalation (intrinsic).
Governing method: Phase-3a hypothesis lane of systematic-attacking; leads only into the
verification spine. Authorized in-scope targets only.
Method
- Map every place a request's path/route is parsed more than once: gateway vs. origin, batch/GraphQL/
JSON-RPC sub-request processors, reverse-proxy rewrite rules, framework
parse_urlcalls (katanato crawl, source-map +semgrepto locate dual parsers). - Probe for validation-vs-execution divergence: encoded slashes, dot-segments, nested batch entries, trailing-data, unicode/overlong forms, and matrix params that resolve differently in the two parsers. Watch for a request that authenticates as unauthenticated/safe but reaches a privileged handler.
- Once a confused route reaches a privileged handler, enumerate the injection surface it exposes
(
sqlmapfor SQLi on parameters the confused route stops sanitizing, command sinks) and build the chain to RCE/admin. - PoC: the full unauthenticated request that desynchronizes and lands the privileged/injection
effect, with an
interactsh-clientOOB or scoped-read impact proof. Link-level negative control = the equivalent direct request is correctly rejected by auth. - Capture the differential as a
nucleitemplate / custom detector for variant analysis across the target's other batch/router surfaces.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 46 lines · 56 tokens per session scan A 0c3989dafcc8
parser-differential-route-confusion is a skill published in the GitHub repository mtarcure/claude-vibe-squad (165 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 678 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
agent-operated-software
Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON agent control plane or a thin surface over specialist agent roles.
schema-check
Check a proposed API or data contract against the current contract, real sample payloads, and a compatibility policy, and gate publication behind a refusable verdict with native digest evidence.
software-design-system-design
Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "system design interview", "capacity planning", or "distributed…
software-design-ddd-domain-modeling
Use when architecture work hinges on DDD-style domain modeling: subdomains, bounded contexts, context relationships, aggregate boundaries, and how those decisions shape overview or detailed design artifacts.
software-design-patterns-and-refactoring
Use when architecture or backend work needs pre-code structural guidance from design patterns, or post-code cleanup guidance from refactoring and code-smell-driven improvement.